Grade B
KARTA — spend control for AI agents
lat.rta.karta/guard · v0.1.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Task envelope, budget ledger, kill switch and signed receipts for agents that pay.
Source: https://github.com/mrpkk/onchain-ai-agent
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 6 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (kill_envelope). Require confirmation before the agent calls them. |
What was checked
- https://karta.rta.lat/mcp: answers without auth
Public tools: check_spend, open_envelope, get_envelope, kill_envelope, envelope_evidence, policy_rules
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/lat-rta-karta-guard-e5c61d0d)